© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111015
    Prev
    Next
    INDEX
    Explanations

    granted certiorari

    np_acts-logits-general · gemini-2.5-flash-lite

    unlike lying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    م
    0.53
    ت
    0.46
     مستقل
    0.46
    ledes
    0.45
     saker
    0.44
     magari
    0.43
     quel
    0.42
    CEM
    0.41
    那我
    0.41
     neur
    0.41
    POSITIVE LOGITS
    sleep
    0.53
     말이
    0.51
     безопас
    0.49
     ஏனெ
    0.47
     ອ
    0.46
    uangan
    0.46
     रझा
    0.46
     png
    0.46
     ເ
    0.46
     ibis
    0.46
    Activations Density 0.000%

    No Known Activations